• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.85-92
• /
• 2023

Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.702-714
• /
• 2020

Stock investment is a personal investment technique that has gathered tremendous interest since the reduction in interest rates and tax exemption. However, it is risky especially for those who do not have expert knowledge on stock volatility. Therefore, it is well understood that accurate stock trend prediction can greatly help stock investment, giving birth to a volume of research work in the field. In order to compare different research works and to optimize hyper-parameters for prediction models, it is required to have an evaluation standard that can accurately assess performances of prediction models. However, little research has been done in the area, and conventionally used methods have been employed repeatedly without being rigorously validated. For this reason, we first analyze performance evaluation of stock trend prediction with respect to performance metrics and data composition, and propose a fair evaluation method based on prediction disparity ratio.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.617-628
• /
• 2021

Drought is a major natural disaster that causes serious social and economic losses. Local drought forecasts can provide important information for drought preparedness. In this study, we propose a new machine learning model that predicts drought by using historical drought indices and meteorological data from 10 sites from 1981 to 2020 in the southeastern part of the Korean Peninsula, Busan-Ulsan-Gyeongnam. Using Bayesian optimization techniques, a hyper-parameter-tuned Random Forest, XGBoost, and Light GBM model were constructed to predict the evaporative demand drought index on a 6-month time scale after 1-month. The model performance was compared by constructing a single site model and a regional model, respectively. In addition, the possibility of improving the model performance was examined by constructing a fine-tuned model using data from a individual site based on the regional model.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.475-481
• /
• 2023

Softwares, especially like machine learning applications, affect human's life style tremendously. Accordingly, the importance of the cost model for softwares increases rapidly. As cost models, LOC(Line of Code) and M/M(Man-Month) estimates the quantitative aspects of the software. Differently from them, FP(Function Point) focuses on estimating the functional characteristics of software. FP is efficient in the aspect that it estimates qualitative characteristics. FP, however, has a limit for evaluating machine learning softwares because FP does not evaluate the critical factors of machine learning software. In this paper, we propose an extended function point(ExFP) that extends FP to adopt hyper parameter and the complexity of its optimization as the characteristics of the machine learning applications. In the evaluation reflecting the characteristics of machine learning applications. we reveals the effectiveness of the proposed ExFP.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.103-113
• /
• 2023

In recent years, Unmanned Aerial Vehicles (UAV) have been widely used in various industries. However, as the depend ence on UAV increases rapidly, concerns about the security and safety of UAV are growing. Currently, various vulnerabili ties such as stealing the control right of the UAV or the right to communicate with the UAV in the web application are being disclosed. However, there is a lack of research related to the security of UAV. Therefore, in this paper, a study was conducted to determine whether the packet data was normal or abnormal by collecting packet data of an unmanned aerial vehicle in a HITL(Hardware In The Loop) simulation environment similar to the real environment. In addition, this paper proposes a method for reducing computational cost in the modeling process and increasing the ease of data interpretation, a machine learning-based anomaly detection model that detects abnormal data by learning only normal data, and optimized hyperparameter values.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.239-247
• /
• 2022

Cities are becoming more complex due to rapid industrialization and population growth in modern times. In particular, urban areas are rapidly changing due to housing site development, reconstruction, and demolition. Thus accurate road information is necessary for various purposes, such as High Definition Map for autonomous car driving. In the case of the Republic of Korea, accurate spatial information can be generated by making a map through the existing map production process. However, targeting a large area is limited due to time and money. Road, one of the map elements, is a hub and essential means of transportation that provides many different resources for human civilization. Therefore, it is essential to update road information accurately and quickly. This study uses Semantic Segmentation algorithms Such as LinkNet, D-LinkNet, and NL-LinkNet to extract roads from drone images and then apply hyperparameter optimization to models with the highest performance. As a result, the LinkNet model using pre-trained ResNet-34 as the encoder achieved 85.125 mIoU. Subsequent studies should focus on comparing the results of this study with those of studies using state-of-the-art object detection algorithms or semi-supervised learning-based Semantic Segmentation techniques. The results of this study can be applied to improve the speed of the existing map update process.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.785-796
• /
• 2023

In this study, a methodology for real-time classification and prediction of defects that may appear in PVDF(Polyvinylidene fluoride) sensors, which are widely used for structural integrity monitoring, is proposed. The types of sensor defects appearing according to the sensor attachment environment were classified, and an impact test using an impact hammer was performed to obtain an output signal according to the defect type. In order to cleary identify the difference between the output signal according to the defect types, the time domain statistical features were extracted and a data set was constructed. Among the machine learning based classification algorithms, the learning of the acquired data set and the result were analyzed to select the most suitable algorithm for detecting sensor defect types, and among them, it was confirmed that the highest optimization was performed to show SVM(Support Vector Machine). As a result, sensor defect types were classified with an accuracy of 92.5%, which was up to 13.95% higher than other classification algorithms. It is believed that the sensor defect prediction technique proposed in this study can be used as a base technology to secure the reliability of not only PVDF sensors but also various sensors for real time structural health monitoring.